© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4594
    Prev
    Next
    INDEX
    Explanations

    and also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝗶
    0.65
     forcément
    0.62
     jugando
    0.59
     estudiando
    0.59
     gostaria
    0.59
    म
    0.58
     Архиви
    0.57
     viendo
    0.57
    タ
    0.56
     coba
    0.55
    POSITIVE LOGITS
     and
    0.73
     in
    0.61
     with
    0.61
     from
    0.57
     for
    0.54
     এবং
    0.53
    and
    0.52
     by
    0.52
     போதும்
    0.51
     to
    0.51
    Activations Density 0.582%

    No Known Activations